INDEX

Explanations

variations of the string or symbol related to coding syntax or structure

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Code snippets with angle brackets

np_acts-logits-general · gemini-2.0-flash

endpoints

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SourceChecksum

-0.87

DockStyle

-0.84

 BoxDecoration

-0.75

AddHtmlAttribute

-0.66

apimachinery

-0.66

MessageOf

-0.66

 dataGridView

-0.64

AdapterView

-0.63

makeConstraints

-0.63

joi

-0.62

POSITIVE LOGITS

 itſelf

0.59

 Antarctica

0.57

bibfield

0.56

ſelf

0.56

 purpoſe

0.55

 reaſon

0.54

 nostrils

0.54

FontOfSize

0.53

 sceptre

0.53

 alps

0.53

Activations Density 0.386%

variations of the string or symbol related to coding syntax or structure

Code snippets with angle brackets

endpoints

No Comments

No Known Activations